Image processing method and device, storage medium and electronic equipment

Abstract

The invention relates to an image processing method and device, a storage medium and electronic equipment, and aims to improve the accuracy of image region division so as to obtain a better image region replacement result. The method comprises: performing semantic segmentation processing on an original image, and superposing images before and after semantic segmentation to obtain a target image; based on the color distance, performing dichotomy clustering on the target pixel points corresponding to the first region and all pixel points corresponding to the second region in the target image toobtain two pixel class clusters; determining a pixel class cluster corresponding to the first region and a pixel class cluster corresponding to the second region according to the color distances between the clustering centers of the two pixel class clusters and the pixel mean value of the target region; and dividing pixel points in the target image according to the two pixel class clusters so as to remove the pixel points belonging to the second region from the pixel points included in the first region.

Description

technical field [0001] The present disclosure relates to image processing technologies, and in particular, to an image processing method, device, storage medium, and electronic equipment. Background technique [0002] In daily life, more and more users have the need to beautify images. For example, for an image taken on a cloudy or foggy day, the user usually replaces the sky with a blue sky to improve the beautification of the image. In the above process of replacing the sky with the blue sky, whether the division of the sky area is accurate will directly affect the subsequent replacement effect. [0003] In related technologies, the semantic segmentation technology is mainly used to segment the sky pixels in the image, and then replace these pixels with the corresponding pixels of the blue sky image, so as to realize sky replacement. However, this method cannot achieve the leaf level, resulting in the inability to replace the sky area near the leaf branches in the image,...

AI Technical Summary

Problems solved by technology

However, this method cannot achieve the leaf level, resulting in the inability to replace the sky area near the leaf branches in the image, so that there is an obvious visual abruptness between the replaced sky and the leaves, which cannot better satisfy the user's image quality. beautification needs

Images